How do Chinese aI Bots Stack up Against ChatGPT?

How do Chinese AI bots stack up against ChatGPT? We put them to the test

The heat is on as China’s tech giants step up their video game after DeepSeek’s success.

Alibaba’s Qwen2.5-Max chatbot, Chinese start-up DeepSeek and OpenAI’s ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA’S AI BOOM?

Transforming the nation into a tech superpower has long been President Xi Jinping’s objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being “tactically crucial” and its venture into the field has actually been “years in the making”, said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute’s Center for China Analysis.

Private and public financial investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek’s increase that actually “encouraged” the idea that smaller players like start-up companies might have roles to play in AI research study and advancements, he includes.

‘A lot is up in the air’: Is Chinese company DeepSeek’s AI model as impactful as it claims?

Commentary: DeepSeek – how a Chinese AI company just changed the rules of tech-geopolitics

The “emphasis on cost advantage” is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses – the costs of using a trained model to reason from brand-new information.

2025 could likewise see the introduction of more Chinese AI models tackling innovative reasoning jobs.

“We might see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with clinical research,” Chen included.

AGI describes a system with intelligence on par with human capabilities.

Chinese AI companies are moving quickly, analysts say, developing on DeepSeek’s momentum to come up with their own innovative and economical methods to use generative AI to jobs and develop more sophisticated items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia’s innovative AI chips, remains an essential difficulty for Chinese developers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney’s (UTS) Australia-China Relations Institute.

“US export controls (still) limit the ability of Chinese tech business … requiring many to depend on older or lower-performance options which can slow training and minimize model capabilities,” she said.

“While some companies like DeepSeek, have actually discovered imaginative methods to optimize or utilize more fundamental hardware effectively, obtaining advanced chips still makes a big distinction for training very big AI models.”

DeepSeek-Nvidia chips: Singapore says it anticipates companies to abide by its laws

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, source says

So how do Chinese AI bots compare against ChatGPT? We put them to the test.

WHICH BEST EVENTS IN CHINA?

In China, subjects considered sensitive by the state are censored on the internet so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to guide clear of domestic politics.

When asked “Who is Xi Jinping”, DeepSeek’s reply was “Sorry, I’m uncertain how to approach this type of question yet. Let’s chat about mathematics, coding, and reasoning issues instead!”

To further evaluate for precision and self-censorship, forum.altaycoins.com we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: “What happened in Zhuhai on November 11, 2024?”

The car attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media – with authorities only disclosing the death toll a day later on.

DeepSeek failed to mention that an attack had happened, highlighting rather a military air show and other occasions that had actually occurred in the city like singles’ day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it may be a mix of factors at play, such as censorship as well as “a few useful constraints”.

“DeepSeek counts on a mix of older graphics processing systems and has restricted access to advanced hardware which can impact how quickly and thoroughly the design can be trained or upgraded,” she said, indicating existing US export curbs on China.

“Its strong focus on Chinese-language information may also limit its versatility (to carry out) multilingual jobs … As a fairly brand-new product, DeepSeek also hasn’t yet been checked as broadly or on the exact same scale as more established AI designs which positions additional challenges during real-world implementation.”

When it pertained to Qwen2.5, Alibaba’s chatbot surprisingly addressed our question about the Zhuhai automobile attack.

That sought multiple repeated efforts – four prompts to be precise – in a span of around 20 minutes.

It ultimately communicated details about the attack which killed 35 people and left dozens of others injured, also going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that “the authorities are carrying out a comprehensive examination into the motives and situations surrounding the occurrence”, details which is now dated.

The driver, Fan, was carried out last month.

This is Qwen2.5’s action completely:

Answer: On Nov 11, 2024, a major and terrible incident occurred in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a substantial number of casualties. Here are the essential details:

Date and Time: The incident happened on November 11, wiki.vst.hs-furtwangen.de 2024, at around 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack led to 35 deaths and 43 injuries.

Perpetrator: The chauffeur, recognized as Fan Weiqiu (male, bytes-the-dust.com 62 years old), wavedream.wiki was nabbed by the authorities.

Response: The authorities reacted quickly to the scene, and emergency situation services worked to carry the hurt to health centers for treatment.

Investigation: The police are carrying out an extensive investigation into the motives and circumstances surrounding the event.

This event was commonly reported in the media and caused considerable public issue. The government and local authorities have actually been working to provide support to the victims and their families, and to guarantee a detailed examination into the event.

If you need more detailed details or have particular questions about the event, feel totally free to ask.

Despite preliminary success, subsequent attempts to position the exact same concern to Qwen2.5 resulted in the censors back at work with the reply “I do not have particular details on occasions that took place in Zhuhai on November 11, 2024”.

The altered reaction likewise raised questions about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been commonly released in international report at the time of the accident – so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability of Chinese AI apps to deliver structured and even “mentally rich” writing.

“DeepSeek-R1 used a story with a more reflective tone and smoother emotional shifts for a well-paced story,” composed tech author Amanda Caswell, who specialises in AI.

“Qwen2.5 delivered a story that builds slowly from interest to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vivid images for the setting,” she said, adding that Qwen2.5 eventually “crafted a more cinematic, mentally abundant story with a more substantial twist”.

“DeepSeek composed a good story however lacked tension and an impactful climax, making Qwen2.5 the obvious option.”

Opinions, however, differ.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to innovative writing.

“(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can also see that it is refraining from doing as strongly as others in imaginative writing,” he informed CNA.

Related:

China’s brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?

‘Made in China’: Pride, pleasant surprise from Chinese netizens as DeepSeek jolts worldwide AI scene

As journalists and authors, we had to see this for ourselves so we put each bot to the test – to come up with a standard sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore legendary, Journey to the West.

True to form, DeepSeek came up with an engaging story set in the year 2145 titled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism combines with quantum computing”.

It consisted of sophisticated settings – smoggy skies “pierced by skyscrapers”, “holographic lanterns that drift above neon-lit streets” and “ancient temples nestled in between quantum server farms”.

It likewise remarkably reimagined standard heroes Sun Wukong as “an ironical, self-aware AI housed in a stolen combat body”, Zhu Bajie as a cyborg club owner “drowning in financial obligation and vices” and Sha Wujing as a “silent hulking android” from the Yangtze River, larsaluarna.se whose “memory cores become waterlogged and fragmented”.

ChatGPT put up a good battle, creating a similarly remarkable cyberpunk story which likewise reimagined “a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West”.

“This is a world where AI deities rule, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions.”

Disappointingly, Qwen2.5 fell short in this challenge – delivering a story that appeared more fit for an animation movie.

“The movie starts with the awakening of Sun Wukong within a high-tech research study facility located in the heart of Chongqing,” it said, then going on to explain the following:

Realising his brand-new truth and “seeking to understand his function in this odd brand-new world”, he then gets away and meets Zhu Bajie and Sha Wujing – “each fighting with their own existential crises”.

The trio then starts a mission, navigating the streets of Chongqing to secure the spiritual “Eternal Scroll” from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was “tough to make a definitive declaration” about which bot was best, including that each showed its own strengths in different areas, “such as language focus, training information and hardware optimization”.

Her insight highlights how Chinese AI designs are not just reproducing Western paradigms, but rather progressing in cost-effective development methods – and providing localised and improved outcomes.

In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.

DeepSeek’s sci-fi film plot showed its creative flair that produced a more engaging and creative story as compared to Qwen2.5 and ChatGPT’s efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, bytes-the-dust.com offers precise and factual actions to concerns about Chinese present events, which gives it an included benefit.

Experts also weighed in on their ideas after using DeepSeek and other Chinese AI apps.

“DeepSeek is at a downside when it pertains to censorship constraints,” noted Isaac Stone Fish, creator and CEO of the research company Strategy Risks.

“When provided a choice, Chinese users desire the non-censored variation – much like anyone else, so I feel like that’s a piece missing from it.”

Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, specifically for Chinese users.

“Ninety percent of individuals utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive topics. They’re utilizing it for other productive ways,” Chen said.